There are times when voice-activated systems do not work very well because of background noise or other voices. This is because it is difficult for machines (and humans) to come out a particular voice when there are many others who are talking. This is sometimes called "the problem of cocktails". Yobe was created following research conducted at MIT on how to solve this problem and announced today a $ 1.8 million start-up funding.
The investment comes from Clique Capital Partners, a $ 100 million fund created specifically to fund innovative voice technology. Yobe had previously received $ 790,000 in the form of a SBIR grant from the National Science Foundation in 2016.
Ken Sutton, co-founder and CEO of the company, says Yobe solves a well-rooted problem by identifying a particular voice in noise. This means for example that if you are at a party and want Alexa to play a Spotify playlist, you can (in theory at least), say the waking word of a crowded room, give the command playlist and the device will perform despite the noise. This is because Yobe can locate a voice based on biometric markers, aggressively enhance the volume and then use AI to smooth it out.
As Sutton says, most of these voice interface technologies fail in this situation because they can not distinguish your voice from the background noise, but Yobe is supposed to solve this problem.
Sutton said that the research phase is over and that the funding is to prepare to go to market. "The capital raised is not to continue R & D. The capital raised is to rationalize and optimize [the technology] for deployment. We will be on the market with a product to sell in 30 days, and all the usual suspects are lined up and waiting for us to call with a live demo, "Sutton told TechCrunch.
In the end, the company hopes to fire its chip technology or phone manufacturers and others in a scenario similar to Dolby. Sutton acknowledges that there are many use cases for a solution that could identify a specific voice in the noise or among other voices such as the forces of order, the manufacturers of Hearing aids and meeting transcription services. You can even use the voice as a biometric marker for authentication purposes. But the company decided to focus its first efforts on voice-activated devices as the first marketing strategy.
The company was founded by Sutton and Dr. S. Hamid Nawab, a researcher and researcher at MIT whose work focused on the application of AI to signal processing. Nawab is the chief scientist of the company.
You can watch this video demo to see how Yobe works: